今週の進捗(DU)

微表情認識に関する論文を読み、使用するデータセットと微表情の定義をまとめた。

これらの論文は大体、出現時間が短い表情を微表情と定義し、詳細な説明はない。データセット普通はSMIC, CASME II, SAMMを使う。

⚪Extended Local Binary Patterns for Efficient and Robust Spontaneous Facial Micro-Expression Recognition

·DATA:CASME-II, SMIC, SAMM

·Definition:MEs have a very short duration, local and subtle facial movements.

Typically being no more than 500 ms

先週の進捗(ZHOU)

About making datasets for the training of Vending supermarket, I finished it and update into GitHub(https://mountain.elcs.kyutech.ac.jp/zhou/vending-supermarket-dataset.git). But the problem between the surrounding area of object and background doesn't resolve. I will modify it in the future.

About the using of the datasets on efficientnet, I tried to train on efficientdet, … Continue Reading ››